Filters








3,738 Hits in 9.0 sec

Visual Psychophysics for Making Face Recognition Algorithms More Explainable [article]

Brandon RichardWebster, So Yon Kwon, Christopher Clarizio, Samuel E. Anthony, Walter J. Scheirer
2018 arXiv   pre-print
In this paper, we suggest that visual psychophysics is a viable methodology for making face recognition algorithms more explainable.  ...  A comprehensive set of procedures is developed for assessing face recognition algorithm behavior, which is then deployed over state-of-the-art convolutional neural networks and more basic, yet still widely  ...  The psychophysics testing regime makes it far more difficult for the algorithms, depending on the chosen transformation.  ... 
arXiv:1803.07140v2 fatcat:pbe3tejkzvefxbdpqdqifir4cm

Visual Psychophysics for Making Face Recognition Algorithms More Explainable [chapter]

Brandon RichardWebster, So Yon Kwon, Christopher Clarizio, Samuel E. Anthony, Walter J. Scheirer
2018 Lecture Notes in Computer Science  
In this paper, we suggest that visual psychophysics is a viable methodology for making face recognition algorithms more explainable.  ...  A comprehensive set of procedures is developed for assessing face recognition algorithm behavior, which is then deployed over state-of-the-art convolutional neural networks and more basic, yet still widely  ...  The psychophysics testing regime makes it far more difficult for the algorithms, depending on the chosen transformation.  ... 
doi:10.1007/978-3-030-01267-0_16 fatcat:n6jxubyua5fgnm3hwe7jfchmhu

Fair SA: Sensitivity Analysis for Fairness in Face Recognition [article]

Aparna R. Joshi, Xavier Suau, Nivedha Sivakumar, Luca Zappella, Nicholas Apostoloff
2022 arXiv   pre-print
Moreover, images captured across different attributes, such as gender and race, can also challenge the robustness of a face recognition algorithm.  ...  Visual Psychophysics Sensitivity Analysis (VPSA) [1] provides a way to pinpoint the individual causes of failure by way of introducing incremental perturbations in the data.  ...  VPSA [1] builds on Psyphy to support a similar itemresponse analysis for face recognition. VPSA comprises of a set of procedures developed to make face recognition algorithms more explainable.  ... 
arXiv:2202.03586v2 fatcat:z3mjhsevhzdlndrlbmtsmp2ite

Perceptual Annotation: Measuring Human Vision to Improve Computer Vision

Walter J. Scheirer, Samuel E. Anthony, Ken Nakayama, David D. Cox
2014 IEEE Transactions on Pattern Analysis and Machine Intelligence  
We propose to use visual psychophysics to directly leverage the abilities of human subjects to build better machine learning systems.  ...  Humans possess highly accurate internal recognition and learning mechanisms that are not yet understood, and they frequently have access to more extensive training data through a lifetime of unbiased experience  ...  VISUAL PSYCHOPHYSICS USING TESTMYBRAIN The problem of face detection makes an excellent first case study for a number of reasons.  ... 
doi:10.1109/tpami.2013.2297711 pmid:26353347 fatcat:25xqb43n5rbjbitoxbjhh2xada

A temporal neural network model for object recognition using a biologically plausible decision making layer [article]

Hamed Heidari Gorji, Reza Ebrahimpour (1 and 2) Faculty of Computer Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran School of Cognitive Sciences, Institute for Research in Fundamental Sciences, Tehran, Iran)
2018 arXiv   pre-print
By extracting features temporally as well as utilizing an accumulation to bound decision making model, an object recognition model accounting for both recognition time and accuracy is proposed.  ...  The recognition accuracy and its processing time depend on task properties such as viewing condition, level of noise and etc. Recognition accuracy can be well explained by different models.  ...  Acknowledgements We would like to thank Ali Farokhi-nejad, Farzad Shayanfar and Mahboubeh Habibi for their helpful comments and generously editing this manuscript. Compliance with Ethical Standards  ... 
arXiv:1806.09334v2 fatcat:6aeob6sda5adblp43czjxhm2jq

Neural Mechanisms Underlying Visual Object Recognition

Arash Afraz, Daniel L.K. Yamins, James J. DiCarlo
2014 Cold Spring Harbor Symposia on Quantitative Biology  
models that aim to fully account for the neural encoding and decoding processes that underlie visual object recognition.  ...  population pattern of activity, it must accurately predict behavior for any object recognition task.  ...  More importantly, because we and others assume that the ventral stream is critically important for "invariant object recognition," we wanted the psychophysical tasks to engage that problem.  ... 
doi:10.1101/sqb.2014.79.024729 pmid:26092883 fatcat:qoyf76nuifdrbgchpsrk6hbzwe

Linear integration of sensory evidence over space and time underlies face categorization [article]

Gouki Okazawa, Long Sha, Roozbeh Kiani
2020 bioRxiv   pre-print
The computational properties of these decision-making processes remain underexplored for object recognition.  ...  Visual object recognition relies on elaborate sensory processes that transform retinal inputs to object representations, but it also requires decision-making processes that read out object representations  ...  Waskom, and Koosha Khalvati for helpful discussions.  ... 
doi:10.1101/2020.11.27.396705 fatcat:cc7nc2xkyffhnle2zsvfpoo7um

Two Routes to Face Perception: Evidence From Psychophysics and Computational Modeling

Adrian Schwaninger, Janek S. Lobmaier, Christian Wallraven, Stephan Collishaw
2009 Cognitive Science  
Pre-activation of one form of representation did not facilitate recognition of the other, neither for unfamiliar faces (Exp. 1) nor for familiar faces (Exp. 2).  ...  This indicates a high internal validity of our method for creating configural and featural face stimuli.  ...  categorical information makes some additional contribution to face recognition, either alone, or in interaction with featural or configural cues.  ... 
doi:10.1111/j.1551-6709.2009.01059.x pmid:21585511 fatcat:i6ucmbrycngpfpg5wjqkf2ad5q

Classification of Faces in Man and Machine

Arnulf B.A. Graf, Felix A. Wichmann, Heinrich H. Bülthoff, Bernhard Schölkopf
2006 Neural Computation  
For this, a novel methodology combining human psychophysics and machine learning is introduced. We proceed as follows.  ...  We attempt to shed light on the algorithms humans use to classify images of human faces according to their gender.  ...  Bülthoff for helpful comments and suggestions. A. B. A. G. was supported by a grant from the European Union (IST 2000-29375 COGVIS).  ... 
doi:10.1162/089976606774841611 pmid:16354384 fatcat:ofght2pccjgullrqbisqq6j67u

Object Perception as Bayesian Inference

Daniel Kersten, Pascal Mamassian, Alan Yuille
2004 Annual Review of Psychology  
Recent work in Bayesian theories of visual perception has shown how complexity may be managed and ambiguity resolved through the taskdependent, probabilistic integration of prior object knowledge with  ...  The algorithm has been extended to combine segmentation with the detection and recognition of faces and text (Tu et al. 2003) .  ...  (B) Face recognition is confounded by illumination variation. This type of uncertainty is more typical of the type of variation encountered during natural visual tasks.  ... 
doi:10.1146/annurev.psych.55.090902.142005 pmid:14744217 fatcat:vqggertz4rdq7g5bjnfkvr6awu

Modeling of Biometric Recognition Based on Human Visual System

Fatima Zohra Allam
2020 International Journal of Advanced Trends in Computer Science and Engineering  
It is a more elaborate model on the perception of images based on the behavior of the Human Visual System, or HVS.  ...  In this paper, another alternative is presented for realizing a biometric system for biometric recognition based on the processing of spectral information.  ...  The methods used in our approach are the face and the iris. We briefly explain the principle of facial recognition and iris recognition. Next, we discuss multimodal fusion.  ... 
doi:10.30534/ijatcse/2020/2991.22020 fatcat:6hrfj24z6zgpxjhzrqzgtmselq

Models of object recognition

Maximilian Riesenhuber, Tomaso Poggio
2000 Nature Neuroscience  
Understanding how biological visual systems recognize objects is one of the ultimate goals in computational neuroscience.  ...  We briefly review some recent trends in computational vision and then focus on feedforward, view-based models that are supported by psychophysical and physiological data.  ...  Some of the basic ideas, however, are relevant for biological models. Object recognition in cortex View-based models have also been proposed to explain object recognition in cortex.  ... 
doi:10.1038/81479 pmid:11127838 fatcat:jj5g4uuodbfjfl5aokthavvqv4

A neuromorphic approach to computer vision

Thomas Serre, Tomaso Poggio
2010 Communications of the ACM  
Acknowledgments We thank Jake Bouvrie for his useful feedback on the manuscript, as well as the referees for their valuable comments.  ...  a theory of the visual cortex, aiming to explain immediate recognition, the initial phase of recognition before eye movement and high-level processes take place.  ...  For instance, Heisele et al. 10 designed a hierarchical system for the detection and recognition of faces, an approach based on a hierarchy of "component experts" performing a local search for one facial  ... 
doi:10.1145/1831407.1831425 fatcat:uqu7icoqqbaw7bvg5rkt74tuqy

Human facial illustrations

Bruce Gooch, Erik Reinhard, Amy Gooch
2004 ACM Transactions on Graphics  
We present a method for creating black-and-white illustrations from photographs of human faces.  ...  We evaluate the effectiveness of the resulting images through psychophysical studies to assess accuracy and speed in both recognition and learning tasks.  ...  Riesenfeld, Bill Thompson, Charles Hansen and the University of Utah Graphics Group for their help in this work.  ... 
doi:10.1145/966131.966133 fatcat:kguno32bb5bgdjpiz2ruzimi4q

Page 875 of Psychological Abstracts Vol. 75, Issue 4 [page]

1988 Psychological Abstracts  
Results indicate that recognition of faces from one’s own age group is easier than recognition of faces from outside one’s Own age group and that women recall women’s faces more easily than they recall  ...  Ss, who were tested in groups, were shown slides of faces paired with common Ist names and asked to associate the names and faces for a subsequent recognition test.  ... 
« Previous Showing results 1 — 15 out of 3,738 results